This project performs llama.cpp mixed-precision quantization on DeepSeek-V3-0324, solving the problem of model deployment on edge devices and improving the model's operation efficiency and resource utilization.

Natural Language ProcessingTransformers

KaniTTS is a high-speed, high-fidelity text-to-speech model optimized for real-time conversational AI applications. It adopts a two-stage pipeline architecture, combining a large language model and an efficient audio codec, achieving excellent speed and audio quality. It supports multiple languages and is suitable for edge/server deployment.

Audio ProcessingTransformersMultiple Languages

Zen Nano 0.6B is the smallest model in the Zen model family, optimized for edge deployment and capable of running efficiently on edge devices, providing strong support for related applications.

Natural Language ProcessingSafetensorsEnglish

LFM2 is a new-generation hybrid model developed by Liquid AI, designed specifically for edge AI and device-side deployment. It sets a new standard in terms of quality, speed, and memory efficiency. This model adopts an innovative hybrid Liquid architecture with multiplicative gates and short convolutions, supporting multilingual processing.

Natural Language ProcessingTransformersMultiple Languages

LFM2 is a new-generation hybrid model developed by Liquid AI, designed specifically for edge AI and device-side deployment. This model sets a new standard in terms of quality, speed, and memory efficiency, and is particularly suitable for running in resource-constrained environments.

Natural Language ProcessingGgufMultiple Languages

Hunyuan is a series of efficient large language models open-sourced by Tencent, designed for multi-purpose deployment in various computing environments. From edge devices to high-concurrency production systems, these models can achieve optimal performance with advanced quantization support and ultra-long context capabilities.

Natural Language ProcessingTransformers

AFM-4.5B is a 4.5-billion parameter instruction-tuned model developed by Arcee.ai, designed specifically for enterprise-level applications. It supports multilingual processing and demonstrates excellent performance in various deployment environments from the cloud to the edge.

Natural Language ProcessingTransformersMultiple Languages

LFM2 is a new-generation hybrid model developed by Liquid AI, designed specifically for edge AI and device-side deployment, setting new standards in terms of quality, speed, and memory efficiency.

Natural Language ProcessingGgufMultiple Languages

LFM2 is a new-generation hybrid model developed by Liquid AI, designed specifically for edge AI and device-side deployment, setting new standards in quality, speed, and memory efficiency.

Natural Language ProcessingGgufMultiple Languages

LFM2 is a new-generation hybrid model developed by Liquid AI, designed specifically for edge AI and device-side deployment, setting new standards in quality, speed, and memory efficiency.

Natural Language ProcessingGgufMultiple Languages

LFM2 is a new-generation hybrid model developed by Liquid AI, designed specifically for edge AI and device-side deployment, setting new standards in terms of quality, speed, and memory efficiency.

Natural Language ProcessingTransformersMultiple Languages

LFM2-350M is the second-generation hybrid model developed by Liquid AI, specifically designed for edge AI and device-side deployment. This model sets a new standard in terms of quality, speed, and memory efficiency. It has 350 million parameters, supports multiple languages, and is suitable for edge computing scenarios.

Natural Language ProcessingTransformersMultiple Languages

LFM2 is a new-generation hybrid model developed by Liquid AI, designed specifically for edge AI and device-side deployment, setting new standards in quality, speed, and memory efficiency.

Natural Language ProcessingTransformersMultiple Languages

LFM2-700M is a new-generation hybrid model developed by Liquid AI, designed specifically for edge AI and device-side deployment, setting new standards in terms of quality, speed, and memory efficiency.

Natural Language ProcessingTransformersMultiple Languages

LFM2-350M is a hybrid model developed by Liquid AI, designed for edge AI and device-side deployment, with efficient training and inference capabilities.

Natural Language ProcessingTransformersMultiple Languages

LoggenixMoE133M is a lightweight Mixture of Experts (MoE) causal language model with a total of 133M parameters and 80M active parameters. This model is trained from scratch on a custom dataset containing root cause analysis, code generation, and inference tasks. It supports special tokens for agent capabilities and is suitable for deployment on edge devices and the construction of professional AI agents.

Natural Language ProcessingTransformers

PP-OCRv4_mobile_det is an efficient text detection model optimized for mobile devices developed by the PaddleOCR team, suitable for deployment on edge devices.

The 4-bit AWQ quantized version of Qwen3-8B, optimized for the MLX library, supports 192k token long context processing, suitable for edge device deployment.

Natural Language ProcessingMlx

A Korean-optimized text generation model with instruction-following capability, featuring lightweight design suitable for edge device deployment

Natural Language ProcessingTransformers

GLM-Edge-4B-Chat is a Chinese-English bilingual dialogue model with 4 billion parameters developed by Zhipu AI. It is specifically optimized for edge devices and supports efficient text generation tasks. This model is based on the Transformer architecture, featuring lightweight design and high efficiency, making it suitable for deployment in resource-constrained environments.

Natural Language ProcessingSafetensors